New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Trl Post Training

by burtenshaw in burtenshaw/training-agents

A skill your agent uses when building, reviewing, or editing TRL post-training workflows for agentic applications, including SFT, DPO, GRPO, RLOO, reward modeling, dataset formats, chat templates…

Apache-2.0Auto-check passedAI & LLM Engineering

Install Trl Post Training

skills CLI
$ npx skills add burtenshaw/training-agents --skill trl-post-training -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install burtenshaw/training-agents trl-post-training --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/burtenshaw/training-agents.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/trl-post-training .claude/skills/trl-post-training && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
trl-post-training
GitHub stars
153
Token cost
~599 tokens
SKILL.md length
266 words
Files
6 (incl. references)
Skills in repo
6
Repo updated
First seen
Licence
Apache-2.0

At a glance

A skill your agent uses when building, reviewing, or editing TRL post-training workflows for agentic applications, including SFT, DPO, GRPO, RLOO, reward modeling, dataset formats, chat templates…

  • Works in 5 steps: Identify the training stage: SFT, DPO,… → Confirm the dataset format before… → Pick the smallest smoke run that… → …
  • Editing TRL post-training workflows for agentic applications
  • SKILL.md covers Workflow, Method Selection, Implementation Rules and References
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Trl Post Training is an agent skill from burtenshaw/training-agents. Use when building, reviewing, or editing TRL post-training workflows for agentic applications, including SFT, DPO, GRPO, RLOO, reward modeling, dataset formats, chat templates, assistant/completion-only losses, tool-calling data, reward functions, and challenge progression from SFT to environment-based RL.

Its SKILL.md is about 600 tokens, which your agent loads only when the skill is triggered. The skill folder holds 7 other files, including reference files (for example `agents/openai.yaml`, `references/dataset-formats.md` and `references/grpo-agent-rewards.md`).

It sits in AI & LLM Engineering, covering Fine-tuning and Structured output and tool calling. The repository describes itself as: A repo on resources for training agents. The licence is Apache-2.0.

When your agent uses it

  • Editing TRL post-training workflows for agentic applications
  • Reward modeling
  • Dataset formats
  • Assistant/completion-only losses

Example prompts

  • “/trl-post-training”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Identify the training stage: SFT, DPO, reward modeling, GRPO, RLOO,
  2. Confirm the dataset format before choosing trainer arguments.
  3. Pick the smallest smoke run that exercises tokenization, generation, reward,
  4. Add Trackio for anything long-running or remote.
  5. Document the eval protocol before claiming model improvement.

What it can do on your machine

Read from SKILL.md and the folder at commit ec7cc54. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Trl Post Training loads about 599 tokens when it runs, and up to ~1.6k if it reads all its reference files. Until then it costs about 81 tokens; SKILL.md has 266 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~81
When it runs · the whole SKILL.md, loaded when a task matches
~599
With references · SKILL.md plus every file in references/, read only if the agent opens them
~1.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from burtenshaw/training-agents at commit ec7cc54, republished under its Apache-2.0 licence (© burtenshaw). 266 words, ~599 tokens.

Download SKILL.mdSave it as .claude/skills/trl-post-training/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.
name
trl-post-training
description
Use when building, reviewing, or editing TRL post-training workflows for agentic applications, including SFT, DPO, GRPO, RLOO, reward modeling, dataset formats, chat templates, assistant/completion-only losses, tool-calling data, reward functions, and challenge progression from SFT to environment-based RL.

TRL Post-Training

Use this skill to design or implement post-training tasks with TRL for models that will act as agents.

Workflow

  1. Identify the training stage: SFT, DPO, reward modeling, GRPO, RLOO, environment RL, or distillation-fed retraining.
  2. Confirm the dataset format before choosing trainer arguments.
  3. Pick the smallest smoke run that exercises tokenization, generation, reward, logging, and saving.
  4. Add Trackio for anything long-running or remote.
  5. Document the eval protocol before claiming model improvement.

Method Selection

  • Use SFT first for new formats, tools, domains, and chat behavior.
  • Use $trl-sft for implementation-level SFT tasks, including trace datasets and trl sft configs.
  • Use DPO when there are high-quality chosen/rejected pairs.
  • Use reward modeling when a learned scorer will be reused.
  • Use GRPO when prompts can be scored by a verifier, test, parser, environment, or judge.
  • Use environment GRPO when success depends on multi-step interaction.
  • Use self-distillation to recycle verified traces into later SFT or preference data.

Implementation Rules

  • Prefer TRL trainer/config classes or TRL CLI configs over custom loops.
  • Use conversational messages data for chat and tool-calling agents.
  • Use prompt-only data for online RL methods such as GRPO.
  • For SFT chat data, use assistant-only loss only when the chat template supports assistant span masking.
  • If eval_strategy is enabled, provide an eval_dataset; otherwise set evaluation to off explicitly.
  • Keep reward functions deterministic where possible and log reward components.
  • Keep generated checkpoints and datasets outside this context repo.

References

Read only the needed reference:

  • references/method-ladder.md: stage selection and challenge sequence.
  • references/dataset-formats.md: TRL dataset and chat-template constraints.
  • references/grpo-agent-rewards.md: reward functions for agentic GRPO.
  • references/script-patterns.md: script and config patterns.

© burtenshaw, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 5 other files (references) in .agents/skills/trl-post-training of burtenshaw/training-agents.

  • SKILL.md
  • agents/openai.yaml
  • references/dataset-formats.md
  • references/grpo-agent-rewards.md
  • references/method-ladder.md
  • references/script-patterns.md

Open the folder on GitHubat commit ec7cc54

Compare with similar skills

Trl Post Training next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Trl Post Training compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Trl Post Training this skillburtenshaw/training-agents153—~599Automated safety check: PassApache-2.0
LLM Integrationyonatangross/orchestkit292—~2.7kAutomated safety check: PassMIT
Swift Mlx Lmkellyvv/PhoneClaw1.3k—~3.7kAutomated safety check: PassApache-2.0
Aqua Deploymentoracle/accelerated-data-science125—~2.4kAutomated safety check: PassUPL-1.0
Slime Useryzlnew/infra-skills149—~3.2kAutomated safety check: PassNone
Sft Launchopen-thoughts/OpenThoughts-Agent301—~2.9kAutomated safety check: PassApache-2.0

Similar skills

  • LLM Integration

    yonatangross/orchestkit

    LLM integration patterns for function calling, streaming responses, local inference with Ollama, and fine-tuning customization.

    292 GitHub stars~2.7k tokensUpdated today
    AI & LLM EngineeringAuto-check passed

  • Swift Mlx Lm

    kellyvv/PhoneClaw

    MLX Swift LM - Run LLMs and VLMs on Apple Silicon using MLX.

    1.3k GitHub stars~3.7k tokensUpdated 2 mo ago
    AI & LLM EngineeringAuto-check passed

  • Aqua Deployment

    oracle/accelerated-data-science

    Official

    Deploy LLM models on OCI using AI Quick Actions (AQUA) - single model, multi-model, stacked (LoRA), with GPU shape selection, vLLM configuration, streaming, and tool calling.

    125 GitHub stars~2.4k tokensUpdated 1 mo ago
    AI & LLM EngineeringAuto-check passed

  • Slime User

    yzlnew/infra-skills

    Guide for using SLIME (LLM post-training framework for RL Scaling).

    149 GitHub stars~3.2k tokensUpdated 3 mo ago
    AI & LLM EngineeringAuto-check passed

  • Sft Launch

    open-thoughts/OpenThoughts-Agent

    Launch SFT via python -m hpc.launch --jobtype sft on any cluster (JSC Jupiter GH200, CINECA Leonardo A100, TACC Vista GH200), with EITHER backend — LLaMA-Factory (default) or axolotl (--sftbackend…

    301 GitHub stars~2.9k tokensUpdated 11 days ago
    AI & LLM EngineeringAuto-check passed

  • Planning With Files

    jarrodwatts/claude-code-config

    Transforms workflow to use Manus-style persistent markdown files for planning, progress tracking, and knowledge storage.

    1.1k GitHub starsUsed in 5 repos~967 tokens
    AI & LLM EngineeringAuto-check passed

More from burtenshaw/training-agents

  • Trl Sft

    burtenshaw/training-agents

    A skill your agent uses when designing, implementing, reviewing, or debugging supervised fine-tuning with TRL SFTTrainer or trl sft, especially for agentic models trained on chat messages…

    153 GitHub stars~685 tokensUpdated 27 days ago
    Auto-check passed

  • Agentic Self Distillation

    burtenshaw/training-agents

    A skill your agent uses when designing or reviewing self-distillation workflows for agentic models, including trace collection, teacher or judge feedback, rejection sampling, critique, conversion to…

    153 GitHub stars~354 tokensUpdated 27 days ago
    Auto-check passed

  • Hugging Face CLI Workflows

    burtenshaw/training-agents

    A skill your agent uses when working with Hugging Face CLI or Hub workflows for TRL training, including auth, repositories, uploads, downloads, Jobs, buckets, model persistence, dataset checks…

    153 GitHub stars~298 tokensUpdated 27 days ago
    Auto-check passed

  • Openenv Agentic Rl

    burtenshaw/training-agents

    A skill your agent uses when designing, reviewing, or implementing OpenEnv-style environment interfaces for agentic RL with TRL, including reset/step/state contracts, tasksets, Docker or…

    153 GitHub stars~381 tokensUpdated 27 days ago
    Auto-check passed

  • Trackio Observability

    burtenshaw/training-agents

    A skill your agent uses when instrumenting or inspecting TRL training runs with Trackio, run names, metric schemas, dashboards, logs, grep or ripgrep, SFTP, Hugging Face Job logs, remote artifacts…

    153 GitHub stars~351 tokensUpdated 27 days ago
    Auto-check passed

Categories

Questions about Trl Post Training

What does Trl Post Training do?

A skill your agent uses when building, reviewing, or editing TRL post-training workflows for agentic applications, including SFT, DPO, GRPO, RLOO, reward modeling, dataset formats, chat templates…. Trl Post Training is an agent skill from burtenshaw/training-agents. Use when building, reviewing, or editing TRL post-training workflows for agentic applications, including SFT, DPO, GRPO, RLOO, reward modeling, dataset formats, chat templates, assistant/completion-only losses, tool-calling data, reward functions, and challenge progression from SFT to environment-based RL.

When should I use Trl Post Training?

Trl Post Training fits situations like: editing TRL post-training workflows for agentic applications; reward modeling; dataset formats; assistant/completion-only losses.

How do I install Trl Post Training in Claude Code?

Run `npx skills add burtenshaw/training-agents --skill trl-post-training -a claude-code`. Or copy the skill folder (.agents/skills/trl-post-training in burtenshaw/training-agents) into .claude/skills/trl-post-training in your project. Claude Code loads it when a task matches its description.

How do I install Trl Post Training in Codex?

Run `npx skills add burtenshaw/training-agents --skill trl-post-training -a codex`. Or copy the skill folder (.agents/skills/trl-post-training in burtenshaw/training-agents) into .agents/skills/trl-post-training in your project. Codex loads it when a task matches its description.

Can I use Trl Post Training in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add burtenshaw/training-agents --skill trl-post-training -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/trl-post-training, .gemini/skills/trl-post-training, .github/skills/trl-post-training and .opencode/skills/trl-post-training in your project.

What does Trl Post Training need to run?

SKILL.md names no scripts, command-line tools or credentials: Trl Post Training is instructions for the agent only.

Does Trl Post Training access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Trl Post Training safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Trl Post Training use?

Trl Post Training is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Trl Post Training use?

About 599 tokens (SKILL.md is roughly 2.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 988 tokens, read only when the agent opens those files.

What are the alternatives to Trl Post Training?

Skills that share tags, products or a category with Trl Post Training: LLM Integration (yonatangross/orchestkit, 292 stars), Swift Mlx Lm (kellyvv/PhoneClaw, 1.3k stars), Aqua Deployment (oracle/accelerated-data-science, 125 stars) and Slime User (yzlnew/infra-skills, 149 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Trl Post Training?

burtenshaw (a GitHub user) maintains it in burtenshaw/training-agents, which has 153 GitHub stars. The repository holds 6 skills in this directory. The repository was last updated on September 13, 2026.

Source: burtenshaw/training-agents on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.